Intelligent analysis method for added distribution energy storage of photovoltaic power station

Abstract

The invention provides a photovoltaic power station additional distribution energy storage intelligent analysis method. The method comprises the steps that S1, charging data, discharging data, energy storage data and power generation data of a photovoltaic power station are collected in real time and preprocessed; s2, inputting the preprocessed data into an energy storage analysis model to obtain an optimal energy storage cost value; s3, according to the pre-processed charging data, the pre-processed discharging data and the pre-processed energy storage data, obtaining a residual electric quantity prediction value, and according to the pre-processed power generation data and the pre-processed discharging data, obtaining an expected power generation amount increasing proportion; and S4, introducing a constraint condition to limit and adjust the data to obtain an updated optimal energy storage cost value, an updated residual electric quantity predicted value and an updated expected electric quantity increasing ratio as an energy storage configuration result. The method has the beneficial effect that the benefit maximization of the photovoltaic power station can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station energy storage, and in particular to an intelligent analysis method for additional energy storage in a photovoltaic power station. Background Art

[0002] With the rapid development and application of renewable energy sources such as solar energy, photovoltaic power plants, as an important component of clean energy, have been widely deployed and developed around the world. However, to improve the operational efficiency and economic benefits of photovoltaic power plants, the rational configuration of energy storage systems has become particularly important.

[0003] In order to make full use of renewable energy resources, active distribution networks that actively manage distributed power sources, energy storage systems, and customer bidirectional loads have become an inevitable development trend in distribution networks. Energy storage absorbs and injects electricity into active distribution networks, which has the advantages of peak shaving and valley filling, and reducing network losses. By reasonably adjusting the charging / discharging operation mode of energy storage, it can effectively compensate for the mismatch between distributed power generation output and load demand in the active distribution network, alleviating the real-time balance needs of power generation and load; at the same time, energy storage can also achieve profitability by utilizing the peak-valley electricity price difference.

[0004] However, existing energy storage analysis methods are mostly based on empirical judgment or simple models, lacking scientific data analysis methods and constraint adjustment, making it difficult to accurately reflect the impact of various factors on economic benefits. As a result, energy storage configuration plans in actual scenarios cannot meet the actual operating conditions of photovoltaic power stations and cannot maximize the benefits of photovoltaic power stations. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to maximize the benefits of photovoltaic power stations. In order to overcome the defects of the above-mentioned existing technologies (or related technologies), the present invention provides an intelligent analysis method for adding energy storage to photovoltaic power stations.

[0006] The present invention provides a method for intelligent analysis of additional energy storage in a photovoltaic power station, comprising the following steps: Step S1, collecting charging data, discharging data, energy storage data and power generation data of the photovoltaic power station in real time, and preprocessing the charging data, the discharging data, the energy storage data and the power generation data to obtain corresponding preprocessed charging data, preprocessed discharging data, preprocessed energy storage data and preprocessed power generation data; Step S2, inputting the pre-processed charging data, the pre-processed discharging data, the pre-processed energy storage data, and the pre-processed power generation data into a pre-built energy storage analysis model to obtain an optimal energy storage cost value; Step S3, obtaining a remaining power prediction value based on the preprocessed charging data, the preprocessed discharging data, and the preprocessed energy storage data, and obtaining an expected power generation increase ratio based on the preprocessed power generation data and the preprocessed discharge data; Step S4, introducing constraint conditions, and performing restrictive adjustments on the pre-processed charging data, the pre-processed discharging data, and the pre-processed energy storage data to obtain an updated optimal energy storage cost value, an updated remaining power forecast value, and an updated expected power generation increase ratio, and using the updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio as the energy storage configuration result.

[0007] Compared with the prior art, the intelligent analysis method for adding energy storage to a photovoltaic power station according to the present invention has the following advantages: In the present invention, step S1 is used to collect and preprocess data of the photovoltaic power station, step S2 is used to calculate the optimal energy storage cost value, step S3 is used to calculate the remaining power forecast value and the expected power generation increase ratio, and step S4 is used to introduce constraints to adjust data restrictions and update the energy storage configuration results. The updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio are used to intuitively inform the user of the optimal value of each dimension, and assist the user in determining whether to adopt the above updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio. Constraints are introduced in the entire analysis process to limit and adjust the data, and find the energy storage configuration plan that best meets the economic and technical requirements for the photovoltaic power station, so as to maximize the benefits of the photovoltaic power station.

[0008] In a possible implementation, in step S1, the preprocessing methods adopted include data cleaning, denoising, interpolation and filling, and data normalization.

[0009] In one possible implementation, the pre-processed charging data includes the charging cost and charging power at the current moment, the pre-processed discharging data includes the discharging cost and discharge power at the current moment, the pre-processed energy storage data includes the energy storage cost per unit energy storage capacity of the energy storage system in the photovoltaic power station and the total energy storage capacity of the energy storage system, and the pre-processed power generation data includes the power generation revenue brought by the energy storage system. In step S2, the energy storage analysis system obtains the optimal energy storage cost value based on the charging cost, the charging power, the discharging cost, the discharge power, the energy storage cost, the total energy storage capacity, and the power generation revenue.

[0010] In a possible implementation, in step S2, the optimal energy storage cost value is obtained by the following calculation formula: ; in, represents the optimal energy storage cost value; Indicates the total charge and discharge time; represents the charging cost; represents the charging power; represents the discharge cost; represents the discharge power; represents the energy storage cost; Indicates the total amount of energy storage; represents the power generation income.

[0011] In one possible implementation, the pre-processed charging data includes charging power and charging efficiency, the pre-processed discharging data includes discharging power and discharging efficiency, and the pre-processed energy storage data includes the current real-time remaining power value. In step S3, the remaining power prediction value is obtained by the following calculation formula: ; in, Indicates the predicted value of remaining power; Indicates the real-time remaining power value; represents the discharge efficiency; represents the discharge power; Indicates the time change value; represents the charging power; represents the charging efficiency; Indicates the total charge and discharge time.

[0012] In a possible implementation, the pre-processed discharge data includes discharge power and discharge efficiency, and the pre-processed power generation data includes the power generation power at the current moment. In step S3, the expected power generation increase ratio is obtained by the following calculation formula: ; in, Indicates the expected power generation increase ratio; Indicates the total charge and discharge time; represents the discharge power; represents the discharge efficiency; Indicates the time change value; represents the generated power.

[0013] In a possible implementation, the pre-processed charging data includes charging power, and the pre-processed discharging data includes discharging power. In step S4, the charging power and the discharging power are limited by the following expressions: ; in, represents the charging power; Indicates the maximum charging power; represents the discharge power; Indicates the maximum discharge power; Indicates the total charge and discharge time.

[0014] In a possible implementation, the pre-processed energy storage data includes the total energy storage amount of the energy storage system in the photovoltaic power station. In step S4, the total energy storage amount is limited by the following expression: ; in, Indicates the minimum total energy storage; Indicates the total amount of energy storage; Indicates the maximum total energy storage capacity.

[0015] In one possible implementation, the pre-processed charging data includes the current charging cost and charging power, the pre-processed discharging data includes the current discharging cost and discharging power, and the pre-processed energy storage data includes the energy storage cost per unit energy storage capacity of the energy storage system in the photovoltaic power station and the total energy storage capacity of the energy storage system. In step S4, the budget constraint is performed using the following expression: ; in, represents the charging cost; represents the charging power; represents the discharge cost; represents the discharge power; represents the energy storage cost; Indicates the total amount of energy storage; Indicates the preset budget threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0017] First, those skilled in the art should understand that these embodiments are merely for explaining the technical principles of the embodiments of the present invention and are not intended to limit the scope of protection of the embodiments of the present invention. Those skilled in the art may make adjustments as needed to adapt to specific application scenarios.

[0018] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] See also Figure 1 The present invention discloses an intelligent analysis method for adding energy storage to a photovoltaic power station. The method integrates data analysis and optimization algorithms to quickly construct and analyze the economic benefits of a photovoltaic power station under different electricity prices and scenarios. Specifically, the method includes: Step S1, real-time collection of charging data, discharging data, energy storage data, and power generation data of the photovoltaic power station, and preprocessing the charging data, discharging data, energy storage data, and power generation data to obtain corresponding preprocessed charging data, preprocessed discharging data, preprocessed energy storage data, and preprocessed power generation data; Step S2, inputting the pre-processed charging data, the pre-processed discharging data, the pre-processed energy storage data, and the pre-processed power generation data into a pre-built energy storage analysis model to obtain an optimal energy storage cost value; Step S3, obtaining a remaining power prediction value based on the pre-processed charging data, the pre-processed discharging data, and the pre-processed energy storage data, and obtaining an expected power generation increase ratio based on the pre-processed power generation data and the pre-processed discharge data; Step S4, introduces constraint conditions, and restricts and adjusts the pre-processed charging data, pre-processed discharging data, and pre-processed energy storage data to obtain an updated optimal energy storage cost value, an updated remaining power forecast value, and an updated expected power generation increase ratio, and uses the updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio as the energy storage configuration result.

[0020] In step S2, based on the received pre-processed data, advanced mathematical modeling techniques and optimization algorithms are used to calculate the optimal energy storage configuration for the energy storage system in the photovoltaic power station. In step S4, constraints are introduced, such as restrictions on technical performance indicators (charging and discharging efficiency) and economic factors (energy storage cost and budget), to ensure that the final energy storage configuration has practical application value.

[0021] During specific applications, users provide basic information about the photovoltaic power station and other relevant data through the data input module in the host computer, specifically charging data, discharging data, energy storage data, and power generation data. The host computer system will automatically clean and standardize the above data in preparation for subsequent analysis.

[0022] In subsequent analysis, the energy storage analysis model is used to analyze the input data to find the energy storage configuration that best meets economic and technical requirements. The results not only include the optimal energy storage cost value after the update, but also include important information such as the updated remaining power forecast value and the expected increase in power generation after the update.

[0023] The goal of the energy storage analysis model is to minimize the total cost. The specific calculation formula is as follows: ; in, is the optimal energy storage cost value, Indicates the total charge and discharge time; and Time Charging and discharging costs; and Time Charging power and discharging power; is the energy storage cost per unit of energy storage capacity; is the total energy storage capacity of the energy storage system; It is the power generation benefit brought about by the addition of energy storage systems, which can be calculated based on the expected increase in power generation.

[0024] The following describes the constraints added in step S4, including: 1. Charge and discharge power limit ; in, Indicates charging power; Indicates the maximum charging power; Indicates discharge power; Indicates the maximum discharge power; Indicates the total charge and discharge time; 2. Energy storage capacity limitations ; in, Indicates the minimum total energy storage; Indicates the total amount of energy storage; Indicates the maximum total energy storage; 3. Maximum daily cycle limit ; in, Indicates time Whether a charge-discharge cycle occurs (1 for yes, 0 for no), Indicates the maximum number of cycles allowed per day; 4. Budget constraints ; in, Indicates the total charge and discharge time; represents the charging cost; Indicates charging power; represents the discharge cost; Indicates discharge power; represents the energy storage cost; Indicates the total amount of energy storage; Indicates the preset budget threshold.

[0025] The remaining power forecast value in the energy storage configuration result is calculated as follows: ; in, Indicates the predicted value of remaining power; Indicates the real-time remaining power value; Indicates discharge efficiency; Indicates discharge power; Indicates the time change value; Indicates charging power; Indicates charging efficiency; Indicates the total charge and discharge time.

[0026] The expected increase in power generation in the energy storage configuration results is calculated as follows: ; in, Indicates the expected increase in power generation; Indicates the total charge and discharge time; Indicates discharge power; Indicates discharge efficiency; Indicates the time change value; Indicates the generated power.

[0027] In the specific application process, the investment payback period of the photovoltaic power station can also be calculated as follows: ; in, represents the investment payback period; represents the initial investment cost; Indicates the annual savings amount; Although there is no data correlation between this investment payback period and the updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio, it can be used as auxiliary data to guide users to evaluate the long-term economic benefits of photovoltaic power stations, thereby maximizing economic benefits.

[0028] During the specific application process, a data display module can also be configured and integrated into the visualization screen to display the changing trends of key indicators, which is convenient for users to understand and make decisions, and supports custom configuration options, allowing users to adjust the display style to suit personal preferences. Specifically, the energy storage configuration results are displayed in a detailed report, and the charging cost, charging power, discharge cost, discharge power, energy storage cost, total energy storage, power generation income, real-time remaining power value, time change value, discharge efficiency, charging efficiency, initial investment cost, annual savings amount, power generation power, maximum charging power, maximum discharge power, minimum total energy storage, and maximum total energy storage involved in the calculation process are displayed in a visual chart to help users quickly understand the energy storage configuration results, and can support users to adjust the display content as needed to explore the potential impact under different assumptions. The specific presentation method of the visual chart can be a bar chart, a line chart, etc., which are all common chart formats and are not given in specific chart examples in the present invention.

[0029] During specific applications, the energy storage analysis model can be placed in the model algorithm library for regular updates. It has built-in models of multiple core components, supporting users to input specific component characteristics or develop customized new models. Based on the rich algorithm library, it is convenient to call different optimization strategies and technical methods to incorporate the latest research results and technological advances. Based on user feedback, the model function is continuously optimized, new features and application scenarios are added, and the accuracy and rationality of the energy storage configuration results are improved.

[0030] Based on the above, the objectives of the intelligent analysis method for adding energy storage to photovoltaic power stations in the present invention include: 1. Improve accuracy: Based on detailed data analysis and optimization algorithms, the recommended energy storage configuration plan is ensured to be close to the actual situation, thus improving the prediction accuracy; 2. Improve flexibility: Supports multiple input formats and custom settings to meet the needs of different user groups; 3. Improve usability: User-friendly interface and simple operation process reduce the learning curve and promote widespread adoption; 4. Improve economic benefits: By optimizing energy storage configuration, the amount of abandoned photovoltaic power can be reduced, the amount of power connected to the grid can be increased, and the economic benefits of photovoltaic power stations can be improved; 5. Comprehensive technical support: It provides a complete technical chain from data processing to result interpretation, and offers a powerful auxiliary tool for the design, operation and maintenance of photovoltaic power plants.

[0031] In the description of the present invention, the reference terms "one embodiment", "some embodiments", "in the present embodiment", "specific examples", or "some examples" mean that the specific features, mechanisms, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, mechanisms, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0032] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for intelligent analysis of additional energy storage in photovoltaic power stations, characterized in that: The following steps are involved: Step S1, collecting charging data, discharging data, energy storage data and power generation data of the photovoltaic power station in real time, and preprocessing the charging data, the discharging data, the energy storage data and the power generation data to obtain corresponding preprocessed charging data, preprocessed discharging data, preprocessed energy storage data and preprocessed power generation data; Step S2, inputting the pre-processed charging data, the pre-processed discharging data, the pre-processed energy storage data, and the pre-processed power generation data into a pre-built energy storage analysis model to obtain an optimal energy storage cost value; Step S3, obtaining a remaining power prediction value based on the preprocessed charging data, the preprocessed discharging data, and the preprocessed energy storage data, and obtaining an expected power generation increase ratio based on the preprocessed power generation data and the preprocessed discharge data; Step S4, introducing constraint conditions, and performing restrictive adjustments on the pre-processed charging data, the pre-processed discharging data, and the pre-processed energy storage data to obtain an updated optimal energy storage cost value, an updated remaining power forecast value, and an updated expected power generation increase ratio, and using the updated optimal energy storage cost value, the updated remaining power forecast value, and the updated expected power generation increase ratio as the energy storage configuration result.

2. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: In step S1, the preprocessing methods adopted include data cleaning, denoising, interpolation and filling, and data normalization.

3. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: The pre-processed charging data includes the charging cost and charging power at the current moment, the pre-processed discharging data includes the discharging cost and discharge power at the current moment, the pre-processed energy storage data includes the energy storage cost per unit energy storage capacity of the energy storage system in the photovoltaic power station and the total energy storage capacity of the energy storage system, and the pre-processed power generation data includes the power generation income brought by the energy storage system. In step S2, the energy storage analysis system obtains the optimal energy storage cost value based on the charging cost, the charging power, the discharging cost, the discharge power, the energy storage cost, the total energy storage capacity and the power generation income.

4. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 3, characterized in that: In step S2, the optimal energy storage cost value is obtained by the following calculation formula: ； in, represents the optimal energy storage cost value; Indicates the total charge and discharge time; represents the charging cost; represents the charging power; represents the discharge cost; represents the discharge power; represents the energy storage cost; Indicates the total amount of energy storage; represents the power generation income.

5. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: The pre-processed charging data includes charging power and charging efficiency, the pre-processed discharging data includes discharging power and discharging efficiency, and the pre-processed energy storage data includes the real-time remaining power value at the current moment. In step S3, the remaining power prediction value is obtained by the following calculation formula: ； in, Indicates the predicted value of remaining power; Indicates the real-time remaining power value; represents the discharge efficiency; represents the discharge power; Indicates the time change value; represents the charging power; represents the charging efficiency; Indicates the total charge and discharge time.

6. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: The pre-processed discharge data includes discharge power and discharge efficiency, and the pre-processed power generation data includes the power generation power at the current moment. In step S3, the expected power generation increase ratio is obtained by the following calculation formula: ； in, Indicates the expected power generation increase ratio; Indicates the total charge and discharge time; represents the discharge power; represents the discharge efficiency; Indicates the time change value; represents the generated power.

7. The method for intelligent analysis of additional energy storage in photovoltaic power plants according to claim 1, characterized in that: The pre-processed charging data includes charging power, and the pre-processed discharging data includes discharging power. In step S4, the charging power and the discharging power are limited by the following expressions: ； in, represents the charging power; Indicates the maximum charging power; represents the discharge power; Indicates the maximum discharge power; Indicates the total charge and discharge time.

8. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: The pre-processed energy storage data includes the total energy storage amount of the energy storage system in the photovoltaic power station. In step S4, the total energy storage amount is limited by the following expression: ； in, Indicates the minimum total energy storage; Indicates the total amount of energy storage; Indicates the maximum total energy storage capacity.

9. The method for intelligent analysis of additional energy storage in photovoltaic power stations according to claim 1, characterized in that: The pre-processed charging data includes the current charging cost and charging power, the pre-processed discharging data includes the current discharging cost and discharging power, and the pre-processed energy storage data includes the energy storage cost per unit energy storage capacity of the energy storage system in the photovoltaic power station and the total energy storage capacity of the energy storage system. In step S4, the budget constraint is performed using the following expression: ； in, Indicates the total charge and discharge time; represents the charging cost; represents the charging power; represents the discharge cost; represents the discharge power; represents the energy storage cost; Indicates the total amount of energy storage; Indicates the preset budget threshold.

Images